{
 "id": "SEACrowd/vilexnorm",
 "owner": "SEACrowd",
 "name": "vilexnorm",
 "downloads": 34,
 "likes": 0,
 "last_modified": "2024-06-24T13:27:06.000Z",
 "stated_licence": "cc-by-nc-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc-by-nc-sa-4.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "multilexnorm"
 ],
 "citation": "@inproceedings{nguyen-etal-2024-vilexnorm,\n    title = \"{V}i{L}ex{N}orm: A Lexical Normalization Corpus for {V}ietnamese Social Media Text\",\n    author = \"Nguyen, Thanh-Nhi  and\n      Le, Thanh-Phong  and\n      Nguyen, Kiet\",\n    editor = \"Graham, Yvette  and\n      Purver, Matthew\",\n    booktitle = \"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)\",\n    month = mar,\n    year = \"2024\",\n    address = \"St. Julian{'}s, Malta\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2024.eacl-long.85\",\n    pages = \"1421--1437\",\n    abstract = \"Lexical normalization, a fundamental task in Natural Language Processing (NLP), involves the transformation of words into their canonical forms. This process has been proven to benefit various downstream NLP tasks greatly.\n    In this work, we introduce Vietnamese Lexical Normalization (ViLexNorm), the first-ever corpus developed for the Vietnamese lexical normalization task. The corpus comprises over 10,000 pairs of sentences meticulously annotated\n    by human annotators, sourced from public comments on Vietnam{'}s most popular social media platforms. Various methods were used to evaluate our corpus, and the best-performing system achieved a result of 57.74% using\n    the Error Reduction Rate (ERR) metric (van der Goot, 2019a) with the Leave-As-Is (LAI) baseline. For extrinsic evaluation, employing the model trained o",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "e3bdc999fb7600da2897a42513e0b0ee81389192",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/vilexnorm/blob/e3bdc999fb7600da2897a42513e0b0ee81389192/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/vilexnorm/blob/e3bdc999fb7600da2897a42513e0b0ee81389192/LICENSE",
 "card_nc": false
}